Visible to the public Pseudo Label Based Unsupervised Deep Discriminative Hashing for Image Retrieval

TitlePseudo Label Based Unsupervised Deep Discriminative Hashing for Image Retrieval
Publication TypeConference Paper
Year of Publication2017
AuthorsHu, Qinghao, Wu, Jiaxiang, Cheng, Jian, Wu, Lifang, Lu, Hanqing
Conference NameProceedings of the 2017 ACM on Multimedia Conference
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-4906-2
Keywordscompositionality, deep hashing, hash algorithms, pseudo labels, pubcrawl, Resiliency, unsupervised hashing

Hashing methods play an important role in large scale image retrieval. Traditional hashing methods use hand-crafted features to learn hash functions, which can not capture the high level semantic information. Deep hashing algorithms use deep neural networks to learn feature representation and hash functions simultaneously. Most of these algorithms exploit supervised information to train the deep network. However, supervised information is expensive to obtain. In this paper, we propose a pseudo label based unsupervised deep discriminative hashing algorithm. First, we cluster images via K-means and the cluster labels are treated as pseudo labels. Then we train a deep hashing network with pseudo labels by minimizing the classification loss and quantization loss. Experiments on two datasets demonstrate that our unsupervised deep discriminative hashing method outperforms the state-of-art unsupervised hashing methods.

Citation Keyhu_pseudo_2017